@plurnk/plurnk-providers 1.3.12 → 1.5.0

package/SPEC.md

@@ -8,8 +8,9 @@ ordinary provider protocols.
 
 The provider stack has four owners:
 
-1. Models.dev supplies a build-time snapshot of provider package, API endpoint,
-   credential names, models, context windows, output limits, and USD prices.
+1. Models.dev supplies a release-time snapshot of provider package, API
+   endpoint, credential names, models, context windows, output limits,
+   reasoning capability, and USD prices.
 2. Official AI SDK providers own vendor request and response protocols.
 3. This package owns the PLURNK contract: aliases, envelopes, normalized usage
    and errors, evidence, local capabilities, and first-party metadata.
@@ -23,7 +24,8 @@ provider declaration, or left explicitly unknown.
 
 ## §2 Provider interface
 
-`Provider` exposes immutable model facts and one generation operation:
+§provider-interface `Provider` exposes immutable model facts and one generation
+operation:
 
 ```ts
 interface Provider {
@@ -35,26 +37,57 @@ interface Provider {
   readonly reasoningReserve?: number | null;
   readonly completionReserve?: number | null;
 
-  countTokens(text: string): number;
+  countPromptTokens(
+    messages: readonly ChatMessage[],
+    signal?: AbortSignal,
+  ): Promise<PromptTokenMeasurement>;
   tokenize?(text: string): Promise<number[]>;
   calculateCost(usage: ProviderUsage): number;
+  calculateCharge?(usage: ProviderUsage): Exclude<ProviderCost, { kind: "authoritative" }>;
   generate(args: GenerateArgs): Promise<ProviderResponse>;
 }
 ```
 
-`contextWindow: null` means genuinely unknown. A consumer MUST NOT invent a
-stand-in. A cataloged cloud model without a context window fails construction
-unless the operator pins `PLURNK_PROVIDERS_CONTEXT_WINDOW`. A local probe
-failure degrades to `null` and emits one warning because a transient probe
-failure must not make a usable local endpoint unbootable.
-
-`countTokens` is synchronous and non-negative. The common fallback is a
-conservative chars/2 ruler and is announced once. `tokenize` exists only when
-the endpoint exposes its real vocabulary.
-
-`calculateCost` returns estimated USD. Models.dev rates are converted at the
-provider boundary. Unknown pricing returns `0`; it is not represented as a
-fabricated rate.
+`contextWindow` is provider physics and resolves under
+{§model-fact-resolution}. `null` means genuinely unknown; a consumer MUST NOT
+invent a stand-in. The context-window knob never carries model-facing prompt
+policy or grinder pressure.
+
+`PromptTokenMeasurement` is a discriminated request-level result:
+
+| `kind`        | Meaning                                                | May authorize physical admission |
+| ------------- | ------------------------------------------------------ | -------------------------------- |
+| `exact`       | Exact count for the complete provider request.         | Yes.                             |
+| `upper_bound` | Proven upper bound for the complete provider request.  | Yes.                             |
+| `estimate`    | Empirical prediction with required causal `detail`.    | No.                              |
+
+Every result carries a non-negative integer `tokens` and a non-empty `source`.
+`countPromptTokens` receives the same messages supplied to `generate` and may
+perform cancellable provider I/O. The common fallback is chars/2 over message
+content; it is announced once and reported honestly as an estimate because it
+knows neither the serving vocabulary nor provider-owned request framing.
+An unavailable optional counting endpoint likewise returns an estimate naming
+the cause. A malformed measurement is a provider contract violation and fails
+hard; consumers do not reinterpret it as ordinary unavailability.
+
+`tokenize` is the separate content-token capability and exists only when the
+endpoint exposes its real vocabulary. Content tokenization does not substitute
+for complete-request measurement.
+
+§provider-monetary-evidence One precedence path converts each provider response
+into {§provider-cost} evidence:
+
+| Precedence | Evidence | Result |
+| --- | --- | --- |
+| 1 | A documented monetary field on that response | The adapter normalizes it as `ProviderResponse.charge`; its decimal USD equivalent wins. |
+| 2 | Exact response usage and the exact model's Models.dev rates | `calculateCharge` returns estimated USD, or explicit free when every applicable rate is zero. |
+| 3 | Neither | Unknown; no cost is reported. |
+
+Models.dev is the sole supported fallback rate table. Missing usage or rates
+never proves free. The numeric `calculateCost` method remains callable only as a
+frozen 1.x compatibility surface and is not a monetary-reporting authority.
+`providerCostUsd` exposes authoritative, estimated, and free evidence as decimal
+USD and returns `null` for unknown evidence.
 
 ### Generation
 
@@ -64,13 +97,13 @@ fabricated rate.
 - caller cancellation through `signal`;
 - optional `grammar` and `maxTokens`;
 - standard `sampling` intent;
-- first-party attribution, client, strike, workspace, loop, and turn metadata.
+- opaque attribution tags plus client, strike, workspace, loop, and turn metadata.
 
-It returns the model's raw content and reasoning, normalized usage, normalized
-finish reason, model identity, opaque evidence, optional metadata, and optional
-telemetry. The provider transports and observes model output; it never retries,
-discards, or repairs an otherwise completed exchange because PLURNK grammar did
-not accept it.
+A successful return carries the model's raw content and reasoning, normalized
+usage, normalized finish reason, model identity, opaque evidence, optional
+metadata, and optional notices. The provider transports and observes model
+output; it never retries, discards, or repairs an otherwise completed exchange
+because PLURNK grammar did not accept it.
 
 Usage obeys:
 
@@ -79,13 +112,38 @@ total = prompt + completion + reasoning
 cached ⊆ prompt
 ```
 
-`completion` excludes reasoning. Known vendor finish reasons normalize to
+`completion` excludes reasoning. Ordinary vendor finish reasons normalize to
 `stop`, `length`, `tool_calls`, or `content_filter`; an unknown value becomes
-`null` and emits a warning.
+`null` and emits a warning. `resource_interrupted` is the distinct failed-attempt
+disposition defined by {§provider-interrupted-attempt}.
+
+### Tagged reasoning responses
+
+§provider-tagged-reasoning Structured provider or SDK reasoning fields are
+authoritative. Visible content is interpreted as tagged reasoning only under an
+explicit alias-scoped response style:
+
+| Effective style | Leading content                                            | Normalized result                                                                                         |
+| --------------- | ---------------------------------------------------------- | --------------------------------------------------------------------------------------------------------- |
+| `verbatim`      | Any bytes.                                                 | Content remains exact; only structured reasoning fields populate `reasoning`.                             |
+| `think-tags`    | No exact leading `<think>`.                                | Content remains exact.                                                                                   |
+| `think-tags`    | `<think>reasoning</think>visible`.                         | The first envelope body becomes reasoning; the exact suffix becomes content. Later tags remain literal.  |
+| `think-tags`    | `<think>reasoning` with no close, including a capped turn. | The complete post-open tail becomes reasoning; content is empty.                                         |
+
+Tag projection never runs when readable structured reasoning is already
+present. Streamed and buffered transports converge on this response boundary.
+When the upstream reports only combined output usage, the existing
+sum-preserving text-proportion estimate reclassifies completion versus reasoning
+without changing prompt, cached input, total output, or billed output.
+
+Grammar evidence retains the exact pre-projection sentence and its Unicode
+content offset. Response classification cannot rewrite what a transported GBNF
+rail observed.
 
 ## §3 AI SDK boundary
 
-Cataloged providers instantiate their Models.dev-declared AI SDK package.
+§provider-sdk-boundary Cataloged providers instantiate their
+Models.dev-declared AI SDK package.
 Standard request shaping, streaming, retries, cancellation, timeouts, usage,
 and vendor error parsing belong to the SDK.
 
@@ -100,6 +158,15 @@ PLURNK maps its generic settings to AI SDK call settings:
 Provider-specific options are permitted only where they preserve a documented
 PLURNK product contract the generic SDK surface cannot express.
 
+§deepseek-reasoning-request The direct DeepSeek catalog path maps the common
+reasoning intent to its OpenAI-compatible controls:
+
+| PLURNK mode | `thinking`            | `reasoning_effort`   |
+| ----------- | --------------------- | -------------------- |
+| `off`       | `{ type: disabled }`  | omitted              |
+| `adaptive`  | omitted               | omitted              |
+| `on`        | `{ type: enabled }`   | budget-derived tier  |
+
 The compatible transport is deliberately retained for:
 
 - `openai` local endpoints, including llama-server and vLLM;
@@ -112,7 +179,8 @@ SDK's ordinary transport.
 
 ## §4 Operator configuration
 
-Every operational value is an environment knob documented in `.env.defaults`.
+§provider-configuration Every operational value is an environment knob
+documented in `.env.defaults`.
 There are no hidden tuning constants. Every `PLURNK_PROVIDERS_*` knob may be
 scoped to an alias by appending `_<alias>`; the scoped value wins.
 
@@ -125,12 +193,11 @@ knob's owning contract.
 The universal groups are:
 
 - reasoning activation and optional explicit budget;
+- explicit reasoning response-content style;
 - decode tuning;
 - request, stream-idle, retry, and probe budgets;
 - local GBNF and llama-server capability pins;
 - context-window and generation-envelope overrides;
-- explicit input, cached-input, and output USD-per-million rates for models
-  absent from the snapshot or deliberate operator overrides;
 - opt-in logprob and raw-body capture.
 
 Operator secrets and machine-specific values never belong in committed
@@ -138,10 +205,26 @@ defaults.
 
 ## §5 Resolution
 
-`PLURNK_MODEL_<alias>=<provider>/<model-id>` declares an alias.
+§provider-resolution `PLURNK_MODEL_<alias>=<provider>/<model-id>` declares an
+alias.
 `PLURNK_MODEL=<alias>` selects the boot alias. Model IDs may contain `/`.
 `PLURNK_BASEURL_<alias>` is a per-alias endpoint override.
 
+### §model-fact-resolution Model fact precedence
+
+Provider and model facts resolve independently:
+
+| Fact                 | Natural source                                         | Operator source                                      | Effective value                                                                                                                                        |
+| -------------------- | ------------------------------------------------------ | ---------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| Context window       | Catalog metadata or a local endpoint probe.            | `PLURNK_PROVIDERS_CONTEXT_WINDOW`.                   | Minimum when both exist; the sole value otherwise. A cataloged cloud miss fails construction; a compatible probe miss remains `null` with one warning. |
+| Completion envelope  | Catalog `maxOutput`; there is no live limit probe.     | `PLURNK_PROVIDERS_COMPLETION_RESERVE`.               | An absolute reserve wins. A percentage derives from the effective window and is capped by catalog `maxOutput` when present.                            |
+| Reasoning capability | Catalog `reasoning: true`, exposed by snapshot lookup. | Runtime activation, reserve, and adapter wire style. | The catalog bit is informational; provider construction neither activates nor blocks reasoning from it.                                                |
+| Estimated USD rates  | Models.dev input, output, and optional cache-read rates. | None. | Missing rates produce unknown evidence; explicit all-zero rates produce free evidence. No live price fetch exists. |
+
+Models.dev cache-read cost defaults to its input cost when omitted. Cache-write
+cost remains snapshot information; the current usage record has no cache-write
+quantity to price.
+
 `instantiateProvider` resolves in this order:
 
 1. A Models.dev provider and model, using its declared AI SDK package.
@@ -161,6 +244,11 @@ Model IDs resolve exactly first. A unique catalog suffix is accepted to avoid
 forcing a vendor-owned resource prefix into PLURNK aliases. Ambiguous suffixes
 fail to resolve.
 
+The catalog package identifies the protocol family, not a mandatory client
+implementation. xAI uses its documented OpenAI-compatible response directly
+because that wire includes exact cost ticks the corresponding AI SDK projection
+omits.
+
 Provider declarations configure facts, not credentials:
 
 ```dotenv
@@ -181,29 +269,35 @@ belongs in MCP, schemes, executors, or mimetypes instead.
 
 A provider plugin:
 
-1. declares `plurnk: { kind: "provider", name }` in `package.json`;
-2. may use any npm scope;
-3. default-exports an AI SDK provider with `languageModel(modelId)`;
-4. peers on compatible `ai` and `@plurnk/plurnk-providers` majors.
+1. declares the exact string `plurnk: { kind: "provider", name }` in `package.json` ({§plugin-family-kind});
+2. may declare always-on package-level `plurnk.attribution` and/or implement the
+   synchronous runtime `attributions(context)` hook under {§plugin-attribution};
+3. may use any npm scope;
+4. default-exports an AI SDK provider with `languageModel(modelId)`;
+5. peers on compatible `ai` and `@plurnk/plurnk-providers` majors.
 
 PLURNK adapts the returned language model. The plugin does not implement the
 PLURNK `Provider`, read PLURNK tuning knobs, or reproduce transport policy.
 
 Discovery is scope-agnostic and memoized per process. Duplicate names fail hard.
-The common plugin trust gate applies before import. A plugin absent from
+The common plugin trust gate applies before import ({§plugin-trust-boundary}). A plugin absent from
 Models.dev requires an explicit context-window pin because PLURNK will not guess
-model physics.
+model physics. `Discovery.packageAttributions` carries the canonical package map;
+the published name-keyed `Discovery.attributions` remains its 1.x projection.
 
 ## §7 Local capabilities
 
-The `openai` local adapter probes `/v1/models`. A llama-server fingerprint may
+§provider-local-capabilities The `openai` local adapter probes `/v1/models`. A
+llama-server fingerprint may
 also expose:
 
 - the actual served model and per-slot context window;
+- request-scoped reasoning parsing and a cumulative response-wide allowance;
 - GBNF constrained sampling;
 - slot count and worker-sticky slot affinity;
 - EOS marker removal;
-- exact `/tokenize`;
+- exact complete-request counting through `/v1/chat/completions/input_tokens`;
+- exact content token IDs through `/tokenize`;
 - the requirement that the caller provide `maxTokens`.
 
 `PLURNK_PROVIDERS_LLAMA_SERVER` may force or disable detection. Probe attempts
@@ -212,9 +306,34 @@ and delay are knobs. A failed probe does not silently assert capabilities.
 Ollama probes `/api/show` for its model context and uses its documented
 OpenAI-compatible generation endpoint through the SDK adapter.
 
+### llama-server reasoning
+
+For a detected llama-server, PLURNK sends the complete reasoning contract on
+every request:
+
+| Mode | Template activation | `thinking_budget_tokens` |
+|---|---:|---:|
+| `off` | false | `0` |
+| `adaptive` | true | resolved reasoning reserve |
+| `on` | true | explicit reasoning budget |
+
+The explicit budget may tighten but MUST NOT exceed the resolved reasoning
+reserve. Template calls normally use `reasoning_format: "auto"` for a separate
+readable channel. A GBNF-bearing call uses `"none"` so the exact constrained
+sentence survives response projection; the adapter separates its leading
+reasoning enclosure only after preserving grammar evidence. Process-wide
+llama-server flags are fallback server configuration, not part of the PLURNK
+contract and need not be synchronized with an alias.
+
+§llama-reasoning-request The allowance is cumulative across the complete response. Opening a second or
+later reasoning block does not replenish it. Template parsing, the reasoning
+sampler, normalized usage, and the returned reasoning channel MUST agree on that
+response boundary.
+
 ## §8 Request authority
 
-The caller's `sampling` bag expresses sampling intent. It cannot override:
+§provider-request-authority The caller's `sampling` bag expresses sampling
+intent. It cannot override:
 
 - model or messages;
 - stream mode;
@@ -235,32 +354,75 @@ backend.
 
 ## §9 Failures, retries, and cancellation
 
-Provider failures normalize to `ProviderError` with source, kind, status where
-available, and the original cause. A caught failure is surfaced or deliberately
-preserved; it is never converted into an empty model turn.
-
-The AI SDK owns attempt scheduling. `PLURNK_PROVIDERS_RETRY_ATTEMPTS` is the
-maximum retry count. Caller cancellation spans the operation. Total and
-stream-chunk deadlines are separately configurable.
+§provider-failure-normalization Provider failures normalize to `ProviderError`.
+Its public contract is an RFC
+9457 Problem Details object with an exact status, stable type, occurrence
+detail, and provider-kind extension; the original error remains its cause.
+A caught failure is surfaced or deliberately preserved; it is never converted
+into an empty model turn or reduced to a message plus a generic status.
+Upstream diagnostic text is bounded by
+`PLURNK_PROVIDERS_ERROR_DETAIL_LIMIT`; the committed `.env.defaults` owns its
+normal value. Retry exhaustion is preserved as `attempts` and
+`retryExhausted`, and the resulting Problem is not marked retryable after the
+provider has consumed its automatic retry budget.
+
+The AI SDK owns one attempt scheduler around the complete generation exchange.
+`PLURNK_PROVIDERS_RETRY_ATTEMPTS` is the maximum retry count, including a
+configured stream-chunk deadline that expires while consuming a response body.
+The total generation deadline and caller cancellation span that scheduler and
+every attempt; neither restarts during replay. Total and stream-chunk deadlines
+are separately configurable.
 
 HTTP 408, 409, 429, and ordinary 5xx responses are retryable unless the endpoint
 explicitly says otherwise. Endpoint control responses 520–527 are final so a
 router can prevent multiplicative retries behind its own retry policy.
 
+### §provider-interrupted-attempt Provider-declared interruption
+
+A successful transport response can still declare that inference did not
+complete. That response is evidence for one failed provider attempt, never a
+completed exchange.
+
+| Concern                    | Contract                                                                                                                     |
+| -------------------------- | ---------------------------------------------------------------------------------------------------------------------------- |
+| Normalized finish reason   | Exact `insufficient_system_resource` becomes `resource_interrupted`; the raw value remains in `assistantRaw`.                |
+| `generate` outcome         | Throw `ProviderError(kind="resource_interrupted")` at local status 503 with the normalized attempt on `error.attempt`.       |
+| Partial response           | Preserve content, reasoning, usage, model, metadata, optional raw body, and other evidence without admitting it as success.  |
+| Automatic replay           | None; the Problem has `retryable: false`, and AI SDK retry scheduling has already completed at the successful transport.     |
+| Capacity-pool overflow     | None; a sibling success would erase the known billed failed attempt from the current `ProviderResponse` surface.             |
+| Consumer admission         | Persist the evidence as an unaccepted attempt; never parse it into executable work, even when its frame looks complete.      |
+
 ## §10 Grammar
 
 GBNF is a local llama-server capability, not a generic provider expectation.
 The consumer chooses whether to supply a grammar. The provider never creates or
 rewrites one.
 
-When transported, output is validated locally after completion. Divergence
-attaches `grammar_unenforced` telemetry with its position; the bytes still
-return. `PLURNK_PROVIDERS_GBNF_DEBUG` validates but withholds the grammar and
-compares the unconstrained result for diagnostics.
+GBNF defines the accepted raw sampled text; it runs before response reasoning
+is separated from regular content. The shipped PLURNK sentence is owned by
+`plurnk-contracts` {§gbnf-turn-shape} and {§gbnf-reasoning-boundary}; this package does
+not restate or rewrite it.
+
+When a grammar-capable adapter receives a grammar, `ProviderResponse` carries
+`grammarEvidence: { input, contentStart, transported }`. `input` is the exact
+pre-projection sentence represented by the response, `contentStart` is its
+Unicode-code-point offset to `assistant.content`, and `transported` says whether
+the grammar was actually sent. Active llama-server template reasoning requests
+the unprojected sentence, records it, and then separates its leading enclosure;
+an empty body therefore remains observable. An endpoint that projects despite
+that request supplies no independent evidence. For an unsplit response, `input`
+is `content` and `contentStart` is zero.
+
+§gbnf-response-observation The provider transports and represents; it does not grade its own enforcement.
+The consumer validates `grammarEvidence.input` outside the enforcer's failure
+domain. `PLURNK_PROVIDERS_GBNF_DEBUG` still validates grammar syntax before the
+call and sets `transported: false` for the unconstrained comparison.
+
 
 ## §11 Evidence and metadata
 
-`assistantRaw` is an opaque normalized transport record. Provider top-level
+§provider-evidence `assistantRaw` is an opaque normalized transport record.
+Provider top-level
 metadata is forwarded as an open bag without reinterpreting currencies or
 vendor fields.
 
@@ -270,25 +432,42 @@ When enabled, raw per-token model logprob is canonical; alternatives are
 preserved when returned. Raw body/chunks preserve wire evidence the normalized
 record omits.
 
-Readable reasoning and encrypted reasoning are separate. Encrypted reasoning is
-preserved verbatim and never decoded or synthesized.
+§provider-encrypted-reasoning **Readable reasoning and encrypted reasoning are
+separate.** Encrypted payload bytes remain opaque and are never decoded. The
+provider boundary distinguishes preserved detail evidence from derived entity
+classification:
+
+| Provider fact                    | Meaning |
+| -------------------------------- | ------- |
+| `id`                             | The provider's reasoning-detail identity, or `null`; never an AG-UI message or tool-call identity. |
+| `subtype`                        | A provider-normalized classification supported by wire structure. OpenAI-compatible `message.reasoning_details` is `message`; no PLURNK operation is reclassified as a native tool call. |
+| `encrypted[*].data` / `format`   | Ordered provider evidence, retained without decoding or concatenation across distinct details. |
+
+Unrecognized detail shapes are omitted at this normalization boundary. Core
+may preserve normalized items as forensic evidence, but a client protocol must
+correlate them to an entity it actually created rather than reusing `id`.
 
 ## §12 Generation envelopes
 
-Reasoning and completion reserves are percentages of the resolved context
+§provider-generation-envelope Reasoning and completion reserves are percentages
+of the resolved context
 window or absolute token counts. Absolute pins win. The provider reports the
-resolved reserves; the consumer owns prompt packing and the per-call output cap.
-
-Models.dev `maxOutput` constrains a percentage-derived completion reserve but
-does not override an explicit absolute operator choice. Unknown model physics
-remain unknown.
+resolved reserves; the consumer owns prompt packing and the per-call output
+cap. Model-limit precedence is defined once in {§model-fact-resolution}.
 
 ## §13 Capacity pool
 
-`Pool` fronts interchangeable `Provider` instances. It keeps workers sticky for
+§provider-capacity-pool `Pool` fronts interchangeable `Provider` instances. It
+keeps workers sticky for
 cache locality, selects a healthy sibling for overflow, and preserves the same
 Provider contract. Whether endpoints are interchangeable is a consumer
-decision, not inferred from provider names.
+decision, not inferred from provider names. Overflow is limited to transport
+availability and rate-limit failures that carry no normalized response attempt;
+{§provider-interrupted-attempt} propagates without overflow.
+
+Prompt measurement covers every backend that could receive the request. The
+pool takes the largest result; differing exact counts or any proven bound yield
+an `upper_bound`, while any estimate makes the aggregate an estimate.
 
 ## §14 Conformance
 
@@ -298,8 +477,12 @@ Coverage MUST prove:
 - exact and unique-suffix model lookup;
 - native SDK request mapping and normalized responses;
 - compatible extension preservation;
-- timeout, retry, cancellation, and final-error behavior;
+- timeout, retry, cancellation, interrupted-attempt, and final-error behavior;
 - local capability probes and pins;
+- exact, bounded, and estimated complete-request token measurements;
+- local reasoning activation, response-wide allowance, and GBNF coexistence;
+- explicit tagged-reasoning projection across streamed, buffered, capped, and
+  literal-tag responses;
 - usage, costs, evidence, metadata isolation, and grammar observation;
 - alias scoping and fail-hard invalid configuration.
 

package/dist/AiSdkProvider.d.ts

@@ -1,21 +1,29 @@
-import type { ChatMessage, Provider, ProviderResponse, ProviderUsage } from "./types.ts";
-import type { Reasoning, ReserveSpec } from "./env.ts";
+import type { AuthoritativeChargeNormalizer, ChatMessage, PromptTokenMeasurement, Provider, ProviderResponse, ProviderUsage } from "./types.ts";
+import type { ProviderCost } from "@plurnk/plurnk-contracts";
+import type { Reasoning, ReasoningResponseStyle, ReserveSpec } from "./env.ts";
 import type { LanguageModel } from "ai";
+import type { PluginAttribution, PluginAttributionContext } from "@plurnk/plurnk-meta";
 export type ProviderFetch = typeof globalThis.fetch;
-export type ReasoningStyle = "none" | "think" | "include_reasoning" | "effort" | "effort_explicit" | "template" | "anthropic";
+export type ReasoningStyle = "none" | "think" | "include_reasoning" | "effort" | "effort_explicit" | "thinking_effort" | "template" | "anthropic";
 export type GrammarStyle = "none" | "llamacpp";
 export type AiSdkProviderConfig = {
     model: string;
     url?: string;
     languageModel?: LanguageModel;
+    attributions?: (context: PluginAttributionContext) => PluginAttribution;
     fetchTimeoutMs: number;
     streamIdleTimeoutMs?: number;
     headers?: Record<string, string>;
     fetch?: ProviderFetch;
     contextWindow?: number | null;
     reasoningStyle?: ReasoningStyle;
-    countTokens?: (text: string) => number;
+    reasoningResponseStyle?: ReasoningResponseStyle;
+    countPromptTokens?: (messages: readonly ChatMessage[], signal?: AbortSignal) => PromptTokenMeasurement | Promise<PromptTokenMeasurement>;
     calculateCost?: (usage: ProviderUsage) => number;
+    calculateCharge?: (usage: ProviderUsage) => Exclude<ProviderCost, {
+        kind: "authoritative";
+    }>;
+    normalizeCharge?: AuthoritativeChargeNormalizer;
     source?: string;
     grammarStyle?: GrammarStyle;
     promptCacheKey?: boolean;
@@ -28,6 +36,7 @@ export type AiSdkProviderConfig = {
     supportsSlotPinning?: boolean;
     slotCount?: number | null;
     tokenizeUrl?: string;
+    promptTokensUrl?: string;
     servedModel?: string;
     requiresMaxTokens?: boolean;
     reasoning: Reasoning;
@@ -39,6 +48,7 @@ export type AiSdkProviderConfig = {
     dryAllowedLength?: number;
     repeatLastN?: number;
     retryAttempts: number;
+    errorDetailLimit?: number;
     topLogprobs?: number | null;
     rawBody?: boolean;
     reasoningReserve?: ReserveSpec;
@@ -48,6 +58,7 @@ export type AiSdkProviderConfig = {
 export declare const effortFromBudget: (budget: number) => "low" | "medium" | "high";
 export default class AiSdkProvider implements Provider {
     #private;
+    readonly attributions?: (context: PluginAttributionContext) => PluginAttribution;
     tokenize?: (text: string) => Promise<number[]>;
     constructor(config: AiSdkProviderConfig);
     get contextWindow(): number | null;
@@ -57,8 +68,11 @@ export default class AiSdkProvider implements Provider {
     get servedModel(): string | undefined;
     get requiresMaxTokens(): boolean | undefined;
     get constrainsOutput(): boolean;
-    countTokens(text: string): number;
+    countPromptTokens(messages: readonly ChatMessage[], signal?: AbortSignal): Promise<PromptTokenMeasurement>;
     calculateCost(usage: ProviderUsage): number;
+    calculateCharge(usage: ProviderUsage): Exclude<ProviderCost, {
+        kind: "authoritative";
+    }>;
     generate({ messages, workerId, primaryWorkerId, signal, grammar, maxTokens, attributions, client, strikes, workspaceId, loop, turn, sampling }: {
         messages: ChatMessage[];
         workerId: string;

package/dist/AiSdkProvider.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"AiSdkProvider.d.ts","sourceRoot":"","sources":["../src/AiSdkProvider.ts"],"names":[],"mappings":"AAQA,OAAO,KAAK,EAAE,WAAW,EAAgB,QAAQ,EAAE,gBAAgB,EAAE,aAAa,EAAE,MAAM,YAAY,CAAC;AACvG,OAAO,KAAK,EAAE,SAAS,EAAE,WAAW,EAAE,MAAM,UAAU,CAAC;AAEvD,OAAO,KAAK,EAAE,aAAa,EAAE,MAAM,IAAI,CAAC;AAKxC,MAAM,MAAM,aAAa,GAAG,OAAO,UAAU,CAAC,KAAK,CAAC;AAapD,MAAM,MAAM,cAAc,GAAG,MAAM,GAAG,OAAO,GAAG,mBAAmB,GAAG,QAAQ,GAAG,iBAAiB,GAAG,UAAU,GAAG,WAAW,CAAC;AAI9H,MAAM,MAAM,YAAY,GAAG,MAAM,GAAG,UAAU,CAAC;AAE/C,MAAM,MAAM,mBAAmB,GAAG;IAC9B,KAAK,EAAE,MAAM,CAAC;IACd,GAAG,CAAC,EAAE,MAAM,CAAC;IACb,aAAa,CAAC,EAAE,aAAa,CAAC;IAC9B,cAAc,EAAE,MAAM,CAAC;IACvB,mBAAmB,CAAC,EAAE,MAAM,CAAC;IAC7B,OAAO,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC;IACjC,KAAK,CAAC,EAAE,aAAa,CAAC;IACtB,aAAa,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IAC9B,cAAc,CAAC,EAAE,cAAc,CAAC;IAChC,WAAW,CAAC,EAAE,CAAC,IAAI,EAAE,MAAM,KAAK,MAAM,CAAC;IACvC,aAAa,CAAC,EAAE,CAAC,KAAK,EAAE,aAAa,KAAK,MAAM,CAAC;IACjD,MAAM,CAAC,EAAE,MAAM,CAAC;IAChB,YAAY,CAAC,EAAE,YAAY,CAAC;IAM5B,cAAc,CAAC,EAAE,OAAO,CAAC;IAGzB,WAAW,CAAC,EAAE,MAAM,CAAC;IACrB,SAAS,CAAC,EAAE,OAAO,CAAC;IACpB,SAAS,CAAC,EAAE,OAAO,CAAC;IACpB,kBAAkB,CAAC,EAAE,OAAO,CAAC;IAC7B,qBAAqB,CAAC,EAAE,MAAM,CAAC;IAC/B,OAAO,CAAC,EAAE,MAAM,CAAC;IAEjB,mBAAmB,CAAC,EAAE,OAAO,CAAC;IAC9B,SAAS,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IAI1B,WAAW,CAAC,EAAE,MAAM,CAAC;IAKrB,WAAW,CAAC,EAAE,MAAM,CAAC;IAIrB,iBAAiB,CAAC,EAAE,OAAO,CAAC;IAM5B,SAAS,EAAE,SAAS,CAAC;IAOrB,WAAW,EAAE,MAAM,CAAC;IACpB,aAAa,EAAE,MAAM,CAAC;IAKtB,gBAAgB,CAAC,EAAE,MAAM,CAAC;IAO1B,aAAa,CAAC,EAAE,MAAM,CAAC;IACvB,OAAO,CAAC,EAAE,MAAM,CAAC;IACjB,gBAAgB,CAAC,EAAE,MAAM,CAAC;IAC1B,WAAW,CAAC,EAAE,MAAM,CAAC;IAIrB,aAAa,EAAE,MAAM,CAAC;IAQtB,WAAW,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IAC5B,OAAO,CAAC,EAAE,OAAO,CAAC;IAOlB,gBAAgB,CAAC,EAAE,WAAW,CAAC;IAC/B,iBAAiB,CAAC,EAAE,WAAW,CAAC;IAIhC,YAAY,CAAC,EAAE,OAAO,CAAC;CAC1B,CAAC;AAeF,eAAO,MAAM,gBAAgB,WAAY,MAAM,KAAG,KAAK,GAAG,QAAQ,GAAG,MAIpE,CAAC;AAwCF,MAAM,CAAC,OAAO,OAAO,aAAc,YAAW,QAAQ;;IA6ClD,QAAQ,CAAC,EAAE,CAAC,IAAI,EAAE,MAAM,KAAK,OAAO,CAAC,MAAM,EAAE,CAAC,CAAC;IAE/C,YAAY,MAAM,EAAE,mBAAmB,EAkEtC;IAED,IAAI,aAAa,IAAI,MAAM,GAAG,IAAI,CAAgC;IAQlE,IAAI,gBAAgB,IAAI,MAAM,GAAG,IAAI,CAAyD;IAC9F,IAAI,iBAAiB,IAAI,MAAM,GAAG,IAAI,CAA0D;IAChG,IAAI,KAAK,IAAI,MAAM,CAAwB;IAE3C,IAAI,WAAW,IAAI,MAAM,GAAG,SAAS,CAA8B;IAEnE,IAAI,iBAAiB,IAAI,OAAO,GAAG,SAAS,CAAoC;IAIhF,IAAI,gBAAgB,IAAI,OAAO,CAA0C;IAEzE,WAAW,CAAC,IAAI,EAAE,MAAM,GAAG,MAAM,CAAoC;IACrE,aAAa,CAAC,KAAK,EAAE,aAAa,GAAG,MAAM,CAAuC;IAuN5E,QAAQ,CAAC,EAAE,QAAQ,EAAE,QAAQ,EAAE,eAAe,EAAE,MAAM,EAAE,OAAO,EAAE,SAAS,EAAE,YAAY,EAAE,MAAM,EAAE,OAAO,EAAE,WAAW,EAAE,IAAI,EAAE,IAAI,EAAE,QAAQ,EAAE,EAAE;QAAE,QAAQ,EAAE,WAAW,EAAE,CAAC;QAAC,QAAQ,EAAE,MAAM,CAAC;QAAC,eAAe,CAAC,EAAE,MAAM,CAAC;QAAC,MAAM,CAAC,EAAE,WAAW,CAAC;QAAC,OAAO,CAAC,EAAE,MAAM,CAAC;QAAC,SAAS,CAAC,EAAE,MAAM,CAAC;QAAC,YAAY,CAAC,EAAE,MAAM,EAAE,CAAC;QAAC,MAAM,CAAC,EAAE,MAAM,CAAC;QAAC,OAAO,CAAC,EAAE,MAAM,CAAC;QAAC,WAAW,CAAC,EAAE,MAAM,CAAC;QAAC,IAAI,CAAC,EAAE,MAAM,CAAC;QAAC,IAAI,CAAC,EAAE,MAAM,CAAC;QAAC,QAAQ,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,CAAA;KAAE,GAAG,OAAO,CAAC,gBAAgB,CAAC,CA2Kxc;CACJ"}
+{"version":3,"file":"AiSdkProvider.d.ts","sourceRoot":"","sources":["../src/AiSdkProvider.ts"],"names":[],"mappings":"AAQA,OAAO,KAAK,EAAE,6BAA6B,EAAE,WAAW,EAAmB,sBAAsB,EAAE,QAAQ,EAAE,gBAAgB,EAAE,aAAa,EAAE,MAAM,YAAY,CAAC;AACjK,OAAO,KAAK,EAAE,YAAY,EAAE,MAAM,0BAA0B,CAAC;AAC7D,OAAO,KAAK,EAAE,SAAS,EAAE,sBAAsB,EAAE,WAAW,EAAE,MAAM,UAAU,CAAC;AAE/E,OAAO,KAAK,EAAE,aAAa,EAAE,MAAM,IAAI,CAAC;AAOxC,OAAO,KAAK,EAAE,iBAAiB,EAAE,wBAAwB,EAAE,MAAM,qBAAqB,CAAC;AAGvF,MAAM,MAAM,aAAa,GAAG,OAAO,UAAU,CAAC,KAAK,CAAC;AAIpD,MAAM,MAAM,cAAc,GAAG,MAAM,GAAG,OAAO,GAAG,mBAAmB,GAAG,QAAQ,GAAG,iBAAiB,GAAG,iBAAiB,GAAG,UAAU,GAAG,WAAW,CAAC;AAIlJ,MAAM,MAAM,YAAY,GAAG,MAAM,GAAG,UAAU,CAAC;AAE/C,MAAM,MAAM,mBAAmB,GAAG;IAC9B,KAAK,EAAE,MAAM,CAAC;IACd,GAAG,CAAC,EAAE,MAAM,CAAC;IACb,aAAa,CAAC,EAAE,aAAa,CAAC;IAC9B,YAAY,CAAC,EAAE,CAAC,OAAO,EAAE,wBAAwB,KAAK,iBAAiB,CAAC;IACxE,cAAc,EAAE,MAAM,CAAC;IACvB,mBAAmB,CAAC,EAAE,MAAM,CAAC;IAC7B,OAAO,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC;IACjC,KAAK,CAAC,EAAE,aAAa,CAAC;IACtB,aAAa,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IAC9B,cAAc,CAAC,EAAE,cAAc,CAAC;IAChC,sBAAsB,CAAC,EAAE,sBAAsB,CAAC;IAChD,iBAAiB,CAAC,EAAE,CAAC,QAAQ,EAAE,SAAS,WAAW,EAAE,EAAE,MAAM,CAAC,EAAE,WAAW,KAAK,sBAAsB,GAAG,OAAO,CAAC,sBAAsB,CAAC,CAAC;IACzI,aAAa,CAAC,EAAE,CAAC,KAAK,EAAE,aAAa,KAAK,MAAM,CAAC;IACjD,eAAe,CAAC,EAAE,CAAC,KAAK,EAAE,aAAa,KAAK,OAAO,CAAC,YAAY,EAAE;QAAE,IAAI,EAAE,eAAe,CAAA;KAAE,CAAC,CAAC;IAC7F,eAAe,CAAC,EAAE,6BAA6B,CAAC;IAChD,MAAM,CAAC,EAAE,MAAM,CAAC;IAChB,YAAY,CAAC,EAAE,YAAY,CAAC;IAM5B,cAAc,CAAC,EAAE,OAAO,CAAC;IAGzB,WAAW,CAAC,EAAE,MAAM,CAAC;IACrB,SAAS,CAAC,EAAE,OAAO,CAAC;IACpB,SAAS,CAAC,EAAE,OAAO,CAAC;IACpB,kBAAkB,CAAC,EAAE,OAAO,CAAC;IAC7B,qBAAqB,CAAC,EAAE,MAAM,CAAC;IAC/B,OAAO,CAAC,EAAE,MAAM,CAAC;IAEjB,mBAAmB,CAAC,EAAE,OAAO,CAAC;IAC9B,SAAS,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IAI1B,WAAW,CAAC,EAAE,MAAM,CAAC;IAGrB,eAAe,CAAC,EAAE,MAAM,CAAC;IAKzB,WAAW,CAAC,EAAE,MAAM,CAAC;IAIrB,iBAAiB,CAAC,EAAE,OAAO,CAAC;IAM5B,SAAS,EAAE,SAAS,CAAC;IAOrB,WAAW,EAAE,MAAM,CAAC;IACpB,aAAa,EAAE,MAAM,CAAC;IAKtB,gBAAgB,CAAC,EAAE,MAAM,CAAC;IAK1B,aAAa,CAAC,EAAE,MAAM,CAAC;IACvB,OAAO,CAAC,EAAE,MAAM,CAAC;IACjB,gBAAgB,CAAC,EAAE,MAAM,CAAC;IAC1B,WAAW,CAAC,EAAE,MAAM,CAAC;IAKrB,aAAa,EAAE,MAAM,CAAC;IAItB,gBAAgB,CAAC,EAAE,MAAM,CAAC;IAQ1B,WAAW,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IAC5B,OAAO,CAAC,EAAE,OAAO,CAAC;IAOlB,gBAAgB,CAAC,EAAE,WAAW,CAAC;IAC/B,iBAAiB,CAAC,EAAE,WAAW,CAAC;IAIhC,YAAY,CAAC,EAAE,OAAO,CAAC;CAC1B,CAAC;AAmEF,eAAO,MAAM,gBAAgB,WAAY,MAAM,KAAG,KAAK,GAAG,QAAQ,GAAG,MAIpE,CAAC;AAwBF,MAAM,CAAC,OAAO,OAAO,aAAc,YAAW,QAAQ;;IA6ClD,QAAQ,CAAC,YAAY,CAAC,EAAE,CAAC,OAAO,EAAE,wBAAwB,KAAK,iBAAiB,CAAC;IAMjF,QAAQ,CAAC,EAAE,CAAC,IAAI,EAAE,MAAM,KAAK,OAAO,CAAC,MAAM,EAAE,CAAC,CAAC;IAC/C,YAAY,MAAM,EAAE,mBAAmB,EAkFtC;IAED,IAAI,aAAa,IAAI,MAAM,GAAG,IAAI,CAAgC;IAQlE,IAAI,gBAAgB,IAAI,MAAM,GAAG,IAAI,CAAyD;IAC9F,IAAI,iBAAiB,IAAI,MAAM,GAAG,IAAI,CAA0D;IAChG,IAAI,KAAK,IAAI,MAAM,CAAwB;IAE3C,IAAI,WAAW,IAAI,MAAM,GAAG,SAAS,CAA8B;IAEnE,IAAI,iBAAiB,IAAI,OAAO,GAAG,SAAS,CAAoC;IAIhF,IAAI,gBAAgB,IAAI,OAAO,CAA0C;IAEnE,iBAAiB,CACnB,QAAQ,EAAE,SAAS,WAAW,EAAE,EAChC,MAAM,CAAC,EAAE,WAAW,GACrB,OAAO,CAAC,sBAAsB,CAAC,CA8CjC;IACD,aAAa,CAAC,KAAK,EAAE,aAAa,GAAG,MAAM,CAAuC;IAClF,eAAe,CAAC,KAAK,EAAE,aAAa,GAAG,OAAO,CAAC,YAAY,EAAE;QAAE,IAAI,EAAE,eAAe,CAAA;KAAE,CAAC,CAGtF;IAwLK,QAAQ,CAAC,EAAE,QAAQ,EAAE,QAAQ,EAAE,eAAe,EAAE,MAAM,EAAE,OAAO,EAAE,SAAS,EAAE,YAAY,EAAE,MAAM,EAAE,OAAO,EAAE,WAAW,EAAE,IAAI,EAAE,IAAI,EAAE,QAAQ,EAAE,EAAE;QAAE,QAAQ,EAAE,WAAW,EAAE,CAAC;QAAC,QAAQ,EAAE,MAAM,CAAC;QAAC,eAAe,CAAC,EAAE,MAAM,CAAC;QAAC,MAAM,CAAC,EAAE,WAAW,CAAC;QAAC,OAAO,CAAC,EAAE,MAAM,CAAC;QAAC,SAAS,CAAC,EAAE,MAAM,CAAC;QAAC,YAAY,CAAC,EAAE,MAAM,EAAE,CAAC;QAAC,MAAM,CAAC,EAAE,MAAM,CAAC;QAAC,OAAO,CAAC,EAAE,MAAM,CAAC;QAAC,WAAW,CAAC,EAAE,MAAM,CAAC;QAAC,IAAI,CAAC,EAAE,MAAM,CAAC;QAAC,IAAI,CAAC,EAAE,MAAM,CAAC;QAAC,QAAQ,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,CAAA;KAAE,GAAG,OAAO,CAAC,gBAAgB,CAAC,CA8Oxc;CAEJ"}